Papers › Enhanced Spatio- Temporal Image Encoding for Online Human Activity Recognition

Enhanced Spatio- Temporal Image Encoding for Online Human Activity Recognition

15 Dec 2023International Conference on Machine Learning and Applications (ICMLA) 2023 12archive 2025-07-28

Nassim Mokhtari, Vincent Fer, Alexis Nédélec, Marlene Gilles, Pierre De Loor

Human Activity Recognition (HAR) based on sen-sors data can be seen as a time series classification problem where the challenge is to handle both spatial and temporal dependencies, while focusing on the most relevant data variations. It can be done using 3D skeleton data extracted from a RGB+D camera. In this work, we propose to improve the spatio-temporal image encoding of 3D skeletons captured from a Kinect sensor, by studying the concept of motion energy which focuses mainly on skeleton joints that are the most solicited for an action. This encoding allows us to achieve a better discrimination for the detection of online activities by focusing on the most significant parts of the actions. The article presents this new encoding and its application for HAR using a deep learning model trained on the encoded 3D skeleton data. For this purpose, we proposed to investigate the knowledge transferability of several pre-trained CNNs provided by Keras. The article shows a significant improvement of the accuracy of the learning according to the state of the art.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Activity RecognitionHuman Activity RecognitionTime SeriesTime Series Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human Activity Recognition OAD dataset ESTIE + VGG16 (transfer-learning) Accuracy 95.22 #1 of 3 Archive leaderboard report
Human Activity Recognition OAD dataset STIE + VGG16 (transfer-learning) Accuracy 94.77 #2 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

VGG-16

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections